Sync leaderboard: EOG + EVA, GitHub README 2026-07-23

eog:
old: Claude Fable 5 (with fallback)=51.1, Gemini 3.5 Flash=50.1, GPT-5.5 (xhigh)=46.6, Kimi K3=45.3, Qwen3.7 Max=45
new: Claude Fable 5 (with fallback)=51.1, Gemini 3.5 Flash=50.1, Muse Spark 1.1 (xhigh)=47.2, GPT-5.5 (xhigh)=46.6, Kimi K3=45.3

.claude/skills/sync-nowai-leaderboard/github-readme/README.md

@@ -43,7 +43,7 @@ Voice agents evaluated on task accuracy (EVA-Accuracy) and conversational experi
 <!-- LEADERBOARD:START -->
 <!-- Auto-generated from data/leaderboard.json by render-readme.mjs. Do not edit by hand. -->
 
-_Snapshot synced 2026-07-17. See the live leaderboards for the full, always-current rankings._
+_Snapshot synced 2026-07-23. See the live leaderboards for the full, always-current rankings._
 
 ### EnterpriseOps-Gym — Top 5
 
@@ -53,9 +53,9 @@ _Task Success Rate · Oracle mode_
 | ---: | :--- | :--- | ---: |
 | 1 | Claude Fable 5 (with fallback) | Anthropic | 51.1% |
 | 2 | Gemini 3.5 Flash | Google | 50.1% |
-| 3 | GPT-5.5 (xhigh) | OpenAI | 46.6% |
-| 4 | Kimi K3 | Kimi | 45.3% |
-| 5 | Qwen3.7 Max | Alibaba | 45.0% |
+| 3 | Muse Spark 1.1 (xhigh) | Muse | 47.2% |
+| 4 | GPT-5.5 (xhigh) | OpenAI | 46.6% |
+| 5 | Kimi K3 | Kimi | 45.3% |
 
 ### EVA-Bench — Top 3
 

data/leaderboard.json

@@ -1,15 +1,15 @@
 {
-  "updated": "2026-07-17T21:00:09.508Z",
+  "updated": "2026-07-23T21:00:12.551Z",
   "sources": {
     "eog": {
       "url": "https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa/",
-      "hash": "sha256:617ad42070acaf5d70ca7782c7f1e4960d26f56cd228667a86f89d51abc580c8",
-      "fetchedAt": "2026-07-17T21:00:09.508Z"
+      "hash": "sha256:a6b866aff1f6925b3ffca8d6428f1cc009d91a1a9bbcef7a72db7991bf800fc9",
+      "fetchedAt": "2026-07-23T21:00:12.551Z"
     },
     "eva": {
       "url": "https://raw.githubusercontent.com/ServiceNow/eva/main/website/src/data/leaderboardStats.json",
       "hash": "sha256:e71bd9e18c294322e706ebc9ca8ac477be01c8caf5d9c25b3121566753f35b77",
-      "fetchedAt": "2026-07-17T21:00:09.508Z"
+      "fetchedAt": "2026-07-23T21:00:12.551Z"
     }
   },
   "eog": {
@@ -31,24 +31,24 @@
       },
       {
         "rank": 3,
+        "model": "Muse Spark 1.1 (xhigh)",
+        "org": "Muse",
+        "score": 47.2,
+        "bar": 47
+      },
+      {
+        "rank": 4,
         "model": "GPT-5.5 (xhigh)",
         "org": "OpenAI",
         "score": 46.6,
         "bar": 47
       },
       {
-        "rank": 4,
+        "rank": 5,
         "model": "Kimi K3",
         "org": "Kimi",
         "score": 45.3,
         "bar": 45
-      },
-      {
-        "rank": 5,
-        "model": "Qwen3.7 Max",
-        "org": "Alibaba",
-        "score": 45,
-        "bar": 45
       }
     ]
   },